Published 13 Jan 2020

Deep learning, computer-aided radiography reading for tuberculosis – A diagnostic accuracy study from a tertiary hospital in India

Author: Madlen Nash 1, 2, Rajagopal Kadavigere' 3, Jasbon Andrade 3, Cynthia Amrutha Sukumar 4, Kiran Chawla 5, Vishnu Prasad Shenoy 5, Tripti Pande 2, Sophie Huddart 1, 2, Madhukar Pai 1, 2, 7, Kavitha Saravu 6, 71

SHARE

https://cms.qure.ai

Back

In general, chest radiographs (CXR) have high sensitivity and moderate specificity for active pulmonary tuberculosis (PTB) screening when interpreted by human readers. However, they are challenging to scale due to hardware costs and the dearth of professionals available to interpret CXR in low-resource, high PTB burden settings. Recently, several computer-aided detection (CAD) programs have been developed to facilitate automated CXR interpretation. We conducted a retrospective case-control study to assess the diagnostic accuracy of a CAD software (qXR, Qure.ai, Mumbai, India) using microbiologically-confirmed PTB as the reference standard. To assess overall accuracy of qXR, receiver operating characteristic (ROC) analysis was used to determine the area under the curve (AUC), along with 95% confidence intervals (CI). Kappa coefficients, and associated 95% CI, were used to investigate inter-rater reliability of the radiologists for detection of specific chest abnormalities. In total, 317 cases and 612 controls were included in the analysis. The AUC for qXR for the detection of microbiologically-confirmed PTB was 0.81 (95% CI: 0.78, 0.84). Using the threshold that maximized sensitivity and specificity of qXR simultaneously, the software achieved a sensitivity and specificity of 71% (95% CI: 66%, 76%) and 80% (95% CI: 77%, 83%), respectively. The sensitivity and specificity of radiologists for the detection of microbiologically-confirmed PTB was 56% (95% CI: 50%, 62%) and 80% (95% CI: 77%, 83%), respectively. For detection of key PTB-related abnormalities ‘pleural effusion’ and ‘cavity’, qXR achieved an AUC of 0.94 (95% CI: 0.92, 0.96) and 0.84 (95% CI: 0.82, 0.87), respectively. For the other abnormalities, the AUC ranged from 0.75 (95% CI: 0.70, 0.80) to 0.94 (95% CI: 0.91, 0.96). The controls had a high prevalence of other lung diseases which can cause radiological manifestations similar to PTB (e.g., 26% had pneumonia, 15% had lung malignancy, etc.). In a tertiary hospital in India, qXR demonstrated moderate sensitivity and specificity for the detection of PTB. There is likely a larger role for CAD software as a triage test for PTB at the primary care level in settings where access to radiologists in limited. Larger prospective studies that can better assess heterogeneity in important subgroups are needed.

Authors

Madlen Nash 1, 2, Rajagopal Kadavigere' 3, Jasbon Andrade 3, Cynthia Amrutha Sukumar 4, Kiran Chawla 5, Vishnu Prasad Shenoy 5, Tripti Pande 2, Sophie Huddart 1, 2, Madhukar Pai 1, 2, 7, Kavitha Saravu 6, 71

Citation

1. Department of Epidemiology 2. Biostatistics and Occupational Health 3. McGill University 4. Montreal 5. Canada 6. McGill International TB Centre 7. McGill University 8. Montreal 9. Canada 10. Department of Radiodiagnosis 11. Kasturba Medical College 12. Manipal 13. Manipal Academy of Higher Education 14. Manipal 15. India 16. Department of Medicine 17. Kasturba Medical College 18. Manipal 19. Manipal Academy of Higher Education 20. Manipal 21. India 22. Department of Microbiology 23. Kasturba Medical College 24. Manipal 25. Manipal Academy of Higher Education 26. Manipal 27. India - - Department of Infectious Diseases 28. Kasturba Medical College 29. Manipal 30. Manipal Academy of Higher Education 31. Manipal 32. India 33. Manipal McGill Program for Infectious Diseases 34. Manipal Centre for Infectious Diseases 35. Prasanna School of Public Health 36. Manipal Academy of Higher Education 37. Manipal 38. India

Share this publication